Merge tag 'drm-intel-fixes-2022-06-16' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

drm/i915 fixes for v5.19-rc3:
- Fix page fault on error state read
- Fix memory leaks in per-gt sysfs
- Fix multiple fence handling
- Remove accidental static from a local variable

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/8735g5xd25.fsf@intel.com

8 files changed, 62 insertions, 47 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index c326bd2b444f..30fe847c6664 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -999,7 +999,8 @@ static int eb_validate_vmas(struct i915_execbuffer *eb)
 			}
 		}
 
-		err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
+		/* Reserve enough slots to accommodate composite fences */
+		err = dma_resv_reserve_fences(vma->obj->base.resv, eb->num_batches);
 		if (err)
 			return err;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 53307ca0eed0..51a0fe60c050 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -785,6 +785,7 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
 {
 	intel_wakeref_t wakeref;
 
+	intel_gt_sysfs_unregister(gt);
 	intel_rps_driver_unregister(&gt->rps);
 	intel_gsc_fini(&gt->gsc);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
index 8ec8bc660c8c..9e4ebf53379b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
@@ -24,7 +24,7 @@ bool is_object_gt(struct kobject *kobj)
 
 static struct intel_gt *kobj_to_gt(struct kobject *kobj)
 {
-	return container_of(kobj, struct kobj_gt, base)->gt;
+	return container_of(kobj, struct intel_gt, sysfs_gt);
 }
 
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
@@ -72,9 +72,9 @@ static struct attribute *id_attrs[] = {
 };
 ATTRIBUTE_GROUPS(id);
 
+/* A kobject needs a release() method even if it does nothing */
 static void kobj_gt_release(struct kobject *kobj)
 {
-	kfree(kobj);
 }
 
 static struct kobj_type kobj_gt_type = {
@@ -85,8 +85,6 @@ static struct kobj_type kobj_gt_type = {
 
 void intel_gt_sysfs_register(struct intel_gt *gt)
 {
-	struct kobj_gt *kg;
-
 	/*
 	 * We need to make things right with the
 	 * ABI compatibility. The files were originally
@@ -98,25 +96,22 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
 	if (gt_is_root(gt))
 		intel_gt_sysfs_pm_init(gt, gt_get_parent_obj(gt));
 
-	kg = kzalloc(sizeof(*kg), GFP_KERNEL);
-	if (!kg)
+	/* init and xfer ownership to sysfs tree */
+	if (kobject_init_and_add(&gt->sysfs_gt, &kobj_gt_type,
+				 gt->i915->sysfs_gt, "gt%d", gt->info.id))
 		goto exit_fail;
 
-	kobject_init(&kg->base, &kobj_gt_type);
-	kg->gt = gt;
-
-	/* xfer ownership to sysfs tree */
-	if (kobject_add(&kg->base, gt->i915->sysfs_gt, "gt%d", gt->info.id))
-		goto exit_kobj_put;
-
-	intel_gt_sysfs_pm_init(gt, &kg->base);
+	intel_gt_sysfs_pm_init(gt, &gt->sysfs_gt);
 
 	return;
 
-exit_kobj_put:
-	kobject_put(&kg->base);
-
 exit_fail:
+	kobject_put(&gt->sysfs_gt);
 	drm_warn(&gt->i915->drm,
 		 "failed to initialize gt%d sysfs root\n", gt->info.id);
 }
+
+void intel_gt_sysfs_unregister(struct intel_gt *gt)
+{
+	kobject_put(&gt->sysfs_gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
index 9471b26752cf..a99aa7e8b01a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
@@ -13,11 +13,6 @@
 
 struct intel_gt;
 
-struct kobj_gt {
-	struct kobject base;
-	struct intel_gt *gt;
-};
-
 bool is_object_gt(struct kobject *kobj);
 
 struct drm_i915_private *kobj_to_i915(struct kobject *kobj);
@@ -28,6 +23,7 @@ intel_gt_create_kobj(struct intel_gt *gt,
 		     const char *name);
 
 void intel_gt_sysfs_register(struct intel_gt *gt);
+void intel_gt_sysfs_unregister(struct intel_gt *gt);
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
 					    const char *name);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index b06611c1d4ad..edd7a3cf5f5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -224,6 +224,9 @@ struct intel_gt {
 	} mocs;
 
 	struct intel_pxp pxp;
+
+	/* gt/gtN sysfs */
+	struct kobject sysfs_gt;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index d078f884b5e3..f0d7b57b741e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -156,7 +156,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
 		[INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) },
 		[INTEL_UC_FW_TYPE_HUC] = { blobs_huc, ARRAY_SIZE(blobs_huc) },
 	};
-	static const struct uc_fw_platform_requirement *fw_blobs;
+	const struct uc_fw_platform_requirement *fw_blobs;
 	enum intel_platform p = INTEL_INFO(i915)->platform;
 	u32 fw_count;
 	u8 rev = INTEL_REVID(i915);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 8521daba212a..1e2750210831 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -166,7 +166,14 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	struct i915_gpu_coredump *gpu;
-	ssize_t ret;
+	ssize_t ret = 0;
+
+	/*
+	 * FIXME: Concurrent clients triggering resets and reading + clearing
+	 * dumps can cause inconsistent sysfs reads when a user calls in with a
+	 * non-zero offset to complete a prior partial read but the
+	 * gpu_coredump has been cleared or replaced.
+	 */
 
 	gpu = i915_first_error_state(i915);
 	if (IS_ERR(gpu)) {
@@ -178,8 +185,10 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 		const char *str = "No error state collected\n";
 		size_t len = strlen(str);
 
-		ret = min_t(size_t, count, len - off);
-		memcpy(buf, str + off, ret);
+		if (off < len) {
+			ret = min_t(size_t, count, len - off);
+			memcpy(buf, str + off, ret);
+		}
 	}
 
 	return ret;
@@ -259,4 +268,6 @@ void i915_teardown_sysfs(struct drm_i915_private *dev_priv)
 
 	device_remove_bin_file(kdev,  &dpf_attrs_1);
 	device_remove_bin_file(kdev,  &dpf_attrs);
+
+	kobject_put(dev_priv->sysfs_gt);
 }
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4f6db539571a..0bffb70b3c5f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/sched/mm.h>
+#include <linux/dma-fence-array.h>
 #include <drm/drm_gem.h>
 
 #include "display/intel_frontbuffer.h"
@@ -1823,6 +1824,21 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 	if (unlikely(err))
 		return err;
 
+	/*
+	 * Reserve fences slot early to prevent an allocation after preparing
+	 * the workload and associating fences with dma_resv.
+	 */
+	if (fence && !(flags & __EXEC_OBJECT_NO_RESERVE)) {
+		struct dma_fence *curr;
+		int idx;
+
+		dma_fence_array_for_each(curr, idx, fence)
+			;
+		err = dma_resv_reserve_fences(vma->obj->base.resv, idx);
+		if (unlikely(err))
+			return err;
+	}
+
 	if (flags & EXEC_OBJECT_WRITE) {
 		struct intel_frontbuffer *front;
 
@@ -1832,31 +1848,23 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 				i915_active_add_request(&front->write, rq);
 			intel_frontbuffer_put(front);
 		}
+	}
 
-		if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
-			err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
-			if (unlikely(err))
-				return err;
-		}
+	if (fence) {
+		struct dma_fence *curr;
+		enum dma_resv_usage usage;
+		int idx;
 
-		if (fence) {
-			dma_resv_add_fence(vma->obj->base.resv, fence,
-					   DMA_RESV_USAGE_WRITE);
+		obj->read_domains = 0;
+		if (flags & EXEC_OBJECT_WRITE) {
+			usage = DMA_RESV_USAGE_WRITE;
 			obj->write_domain = I915_GEM_DOMAIN_RENDER;
-			obj->read_domains = 0;
-		}
-	} else {
-		if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
-			err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
-			if (unlikely(err))
-				return err;
+		} else {
+			usage = DMA_RESV_USAGE_READ;
 		}
 
-		if (fence) {
-			dma_resv_add_fence(vma->obj->base.resv, fence,
-					   DMA_RESV_USAGE_READ);
-			obj->write_domain = 0;
-		}
+		dma_fence_array_for_each(curr, idx, fence)
+			dma_resv_add_fence(vma->obj->base.resv, curr, usage);
 	}
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence)